• Computer Science
  • Published in NIPS 2016

DeepMath - Deep Sequence Models for Premise Selection

@inproceedings{Irving2016DeepMathD,
  title={DeepMath - Deep Sequence Models for Premise Selection},
  author={Geoffrey Irving and Christian Szegedy and Alexander A. Alemi and Niklas E{\'e}n and François Chollet and Josef Urban},
  booktitle={NIPS},
  year={2016}
}
We study the effectiveness of neural sequence models for premise selection in automated theorem proving, one of the main bottlenecks in the formalization of mathematics. We propose a two stage approach for this task that yields good results for the premise selection task on the Mizar corpus while avoiding the hand-engineered features of existing state-of-the-art models. To our knowledge, this is the first time deep learning has been applied to theorem proving on a large scale. 

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 78 CITATIONS

Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Ransomware Triage Using Deep Learning: Twitter as a Case Study

VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Premise Selection for Theorem Proving by Deep Graph Embedding

VIEW 5 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

GAMEPAD: A LEARNING ENVIRONMENT FOR THEO-

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

GamePad: A Learning Environment for Theorem Proving

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Recent Advances in Deep Learning: An Overview

VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2020

CITATION STATISTICS

  • 7 Highly Influenced Citations

  • Averaged 24 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

MizAR 40 for Mizar 40

VIEW 5 EXCERPTS

Long Short-Term Memory

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Hammering towards QED

VIEW 3 EXCERPTS

A Neural Conversational Model

VIEW 1 EXCERPT

A formal proof of the Kepler conjecture

VIEW 1 EXCERPT

End-to-end memory networks

  • S. Sukhbaatar, J. Weston, R. Fergus
  • In Advances in Neural Information Processing Systems,
  • 2015
VIEW 1 EXCERPT